Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    the numeral representations of experimental phases or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Roman numeral II

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    chieht
    -0.58
     jadx
    -0.58
    ieteur
    -0.50
     zoude
    -0.50
     promessa
    -0.49
    범
    -0.48
     gömlek
    -0.47
     tekem
    -0.47
     aihe
    -0.46
     Grom
    -0.46
    POSITIVE LOGITS
     II
    1.86
    II
    1.56
     III
    1.27
    III
    1.10
     ii
    1.10
    IIII
    1.03
     Ii
    1.02
    ii
    0.98
    IIA
    0.96
    Ⅱ
    0.94
    Act Density 0.027%

    No Known Activations